基于GA-BP神经网络的广东淮山产量预测分析

Prediction and Analysis of Guangdong Chinese Yam Yield Based on GA-BP Neural Network

针对传统BP神经网络在产量预测中存在测试精度低、鲁棒性差等问题,利用遗传算法对BP神经网络模型进行了优化,并基于广东省普宁市南溪大陇村2015-2021年间物联网获取的温室环境数据与气象环境数据和淮山产量,采用BP神经网络及GA-BP神经网络模型对所选地区淮山产量建立预测模型并分析。研究结果表明:GA优化后的BP神经网络模型的预测准确度显著高于单一BP神经网络模型,R 2达到0.8858,平均相对误差仅为0.74%,预测更加科学、合理,对淮山生产及区域农业经济管理措施的调整具有重要的指导意义。

Aiming at the problems of low test accuracy and poor robustness in traditional BP neural network in production forecasting,genetic algorithm is used to optimize the BP neural network model.Based in Dalong Village,Nanxi,Puning City,Guangdong Province,Greenhouse environmental data(soil moisture content and soil temperature),meteorological environmental data(atmospheric humidity,atmospheric temperature,rainfall)and yam production from 2014 to 2021,BP neural network and GA-BP neural network model were used to predict the yield of Huaishan in selected areas.The research results show that the prediction accuracy of the GA-BP neural network model is significantly higher than that of the BP neural network model,the R2 reaches 0.8858,and the average relative error is only 0.74%.Through GA-BP prediction,the production of Chinese yam can be predicted more scientifically and reasonably.Therefore,the GA-BP prediction can be used to predict the yield of Chinese yam more scientifically and reasonably,which has important guiding significance for the adjustment of the production of Chinese yam and the adjustment of regional agricultural economic management measures.